Internal:GPU Usage - Revision history

Spyridon97: Spyridon97 moved page Internal:Internal:GPU Usage to Internal:GPU Usage

2020-04-30T21:20:34Z

Spyridon97 moved page Internal:Internal:GPU Usage to Internal:GPU Usage

← Older revision	Revision as of 16:20, 30 April 2020
(No difference)

Spyridon97: Spyridon97 moved page Internal:PODM Refactoring to Internal:Internal:GPU Usage

2020-04-30T21:20:21Z

Spyridon97 moved page Internal:PODM Refactoring to Internal:Internal:GPU Usage

← Older revision	Revision as of 16:20, 30 April 2020
(No difference)

Spyridon97 at 21:20, 30 April 2020

2020-04-30T21:20:01Z

← Older revision		Revision as of 16:20, 30 April 2020
Line 1:		Line 1:
	~~=Code Changes=~~
	~~# Choose a specific C++ coding style✔~~
	~~# Use C++17 standard✔~~
	~~# Remove the CGAL library by replacing its predicates with the following one which is way faster: (TODO)~~
	~~## Benchmark: [https://crtc.cs.odu.edu/Internal:4D_Predicates_Benchmark PCK vs CGAL Predicates Benchmark]~~
	~~## Paper: [https://hal.inria.fr/hal-01225202 Predicate Construction Kit Paper]~~
	~~## Code: [https://gforge.inria.fr/frs/?group_id=5833 Predicate Construction Kit Code]~~
	~~# Remove Boost library by replacing its threads with std::thread (ask Christos for Barrier). (TODO)~~
	~~# Update ITK to the newest version (TODO)~~
	~~# Keep only useful Defines~~
	~~## For PODM3D✔~~
	~~## For PODM4D✔~~

	~~=Abstractions=~~
	~~# Combine 3D and 4D PODM versions into one abstract program, in which the user will choose what he wants to use.~~
	~~## Create namespaces for each PODM which will help to create a templated PODM wrapper✔~~
	~~## Template the common code of each PODM for 3-4 dimensions (or even more or less) (TODO)~~
	~~# Decouple Contentions managers and Load Balancing from the Meshing Procedure (TODO)~~
	~~# Add PDR (TODO)~~
	~~# Add Smoothing (TODO)~~

	=Explore Usage of GPU=		=Explore Usage of GPU=
	# For “itkSignedMaurerParallelDistanceMapImageFilter” code:		# For “itkSignedMaurerParallelDistanceMapImageFilter” code:

Spyridon97: Spyridon97 moved page PODM Refactoring to Internal:PODM Refactoring

2020-04-30T20:41:22Z

Spyridon97 moved page PODM Refactoring to Internal:PODM Refactoring

← Older revision	Revision as of 15:41, 30 April 2020
(No difference)

Spyridon97: /* Code Changes */

2020-03-27T20:10:55Z

Code Changes

← Older revision		Revision as of 15:10, 27 March 2020
Line 7:		Line 7:
	## Code: [https://gforge.inria.fr/frs/?group_id=5833 Predicate Construction Kit Code]		## Code: [https://gforge.inria.fr/frs/?group_id=5833 Predicate Construction Kit Code]
	# Remove Boost library by replacing its threads with std::thread (ask Christos for Barrier). (TODO)		# Remove Boost library by replacing its threads with std::thread (ask Christos for Barrier). (TODO)
	~~# Remove VTK library and replace it with MeshIO (TODO)~~
	# Update ITK to the newest version (TODO)		# Update ITK to the newest version (TODO)
	# Keep only useful Defines		# Keep only useful Defines

Spyridon97: /* Code Changes */

2020-03-27T20:10:29Z

Code Changes

← Older revision		Revision as of 15:10, 27 March 2020
Line 10:		Line 10:
	# Update ITK to the newest version (TODO)		# Update ITK to the newest version (TODO)
	# Keep only useful Defines		# Keep only useful Defines
	## For ~~PODM3D (TODO)~~		## For PODM3D✔
	## For PODM4D✔		## For PODM4D✔

Spyridon97: /* Explore Other Techiniques */

2020-02-25T15:53:09Z

Explore Other Techiniques

← Older revision		Revision as of 10:53, 25 February 2020
Line 21:		Line 21:
	# Add Smoothing (TODO)		# Add Smoothing (TODO)

	=Explore ~~Other Techiniques~~=		=Explore Usage of GPU=
	~~# Use GPUs:~~		# For “itkSignedMaurerParallelDistanceMapImageFilter” code:
	## For “itkSignedMaurerParallelDistanceMapImageFilter” code:		## Understand the code by reading the [https://cepm.cs.odu.edu/pub/papers/journal_23.pdf Parallel N-Dimensional Exact Signed Euclidean Distance Transform] paper
	### Understand the code by reading the [https://cepm.cs.odu.edu/pub/papers/journal_23.pdf Parallel N-Dimensional Exact Signed Euclidean Distance Transform] paper		## Study if it’s beneficial to convert it in order to use GPUs. See the papers:
	### Study if it’s beneficial to convert it in order to use GPUs. See the papers:		### [https://crtc.cs.odu.edu/pub/papers/journal_18.pdf A Multigrain Delaunay Mesh Generation Method for Multicore SMT-based Architectures], (TODO)
	#### [https://crtc.cs.odu.edu/pub/papers/journal_18.pdf A Multigrain Delaunay Mesh Generation Method for Multicore SMT-based Architectures], (TODO)		### [https://crtc.cs.odu.edu/pub/papers/journal_19.pdf Algorithm, Software, and Hardware Optimizations for Delaunay Mesh Generation on Simultaneous Multithreaded Architectures] (TODO)
	#### [https://crtc.cs.odu.edu/pub/papers/journal_19.pdf Algorithm, Software, and Hardware Optimizations for Delaunay Mesh Generation on Simultaneous Multithreaded Architectures] (TODO)		# For Predicates:
	## For Predicates:		## Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)
	### Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)		## Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)
	### Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)

Spyridon97: /* Abstractions */

2020-02-25T15:52:41Z

Abstractions

← Older revision		Revision as of 10:52, 25 February 2020
Line 21:		Line 21:
	# Add Smoothing (TODO)		# Add Smoothing (TODO)

	=Explore Other Techiniques		=Explore Other Techiniques=
	# Use GPUs:		# Use GPUs:
	## For “itkSignedMaurerParallelDistanceMapImageFilter” code:		## For “itkSignedMaurerParallelDistanceMapImageFilter” code:

Spyridon97 at 15:52, 25 February 2020

2020-02-25T15:52:33Z

← Older revision		Revision as of 10:52, 25 February 2020
Line 1:		Line 1:
	=~~==PODM Refactoring==~~=		=Code Changes=
	# Choose a specific C++ coding style✔		# Choose a specific C++ coding style✔
	# Use C++17 standard✔		# Use C++17 standard✔
Line 12:		Line 12:
	## For PODM3D (TODO)		## For PODM3D (TODO)
	## For PODM4D✔		## For PODM4D✔

			=Abstractions=
	# Combine 3D and 4D PODM versions into one abstract program, in which the user will choose what he wants to use.		# Combine 3D and 4D PODM versions into one abstract program, in which the user will choose what he wants to use.
	## Create namespaces for each PODM which will help to create a templated PODM wrapper✔		## Create namespaces for each PODM which will help to create a templated PODM wrapper✔
	## Template the common code of each PODM for 3-4 dimensions (or even more or less) (TODO)		## Template the common code of each PODM for 3-4 dimensions (or even more or less) (TODO)
			# Decouple Contentions managers and Load Balancing from the Meshing Procedure (TODO)
			# Add PDR (TODO)
			# Add Smoothing (TODO)

			=Explore Other Techiniques
	# Use GPUs:		# Use GPUs:
	## For “itkSignedMaurerParallelDistanceMapImageFilter” code:		## For “itkSignedMaurerParallelDistanceMapImageFilter” code:
	### Understand the code by reading the [https://cepm.cs.odu.edu/pub/papers/journal_23.pdf Parallel N-Dimensional Exact Signed Euclidean Distance Transform] paper		### Understand the code by reading the [https://cepm.cs.odu.edu/pub/papers/journal_23.pdf Parallel N-Dimensional Exact Signed Euclidean Distance Transform] paper
	### Study if it’s beneficial to convert it in order to use GPUs. See the papers:		### Study if it’s beneficial to convert it in order to use GPUs. See the papers:
	#### [https://~~cepm~~.cs.odu.edu/pub/papers/journal_18.pdf A Multigrain Delaunay Mesh Generation Method for Multicore SMT-based Architectures], (TODO)		#### [https://crtc.cs.odu.edu/pub/papers/journal_18.pdf A Multigrain Delaunay Mesh Generation Method for Multicore SMT-based Architectures], (TODO)
	#### [https://~~cepm~~.cs.odu.edu/pub/papers/journal_19.pdf Algorithm, Software, and Hardware Optimizations for Delaunay Mesh Generation on Simultaneous Multithreaded Architectures] (TODO)		#### [https://crtc.cs.odu.edu/pub/papers/journal_19.pdf Algorithm, Software, and Hardware Optimizations for Delaunay Mesh Generation on Simultaneous Multithreaded Architectures] (TODO)
	## For Predicates:		## For Predicates:
	### Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)		### Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)
	### Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)		### Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)
	~~# Decouple Contentions managers and Load Balancing from the Meshing Procedure (TODO)~~
	~~# Add PDR (TODO)~~
	~~# Add Smoothing (TODO)~~

Spyridon97: /* PODM Refactoring */

2020-02-25T15:49:43Z

PODM Refactoring

← Older revision		Revision as of 10:49, 25 February 2020
Line 24:		Line 24:
	### Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)		### Based on [https://imr.sandia.gov/_assets/documents/2019_IMR_Papers/6B.1-de%20Matos%20Menezes.pdf ACCELERATING THE EXACT EVALUATION OF GEOMETRIC PREDICATES WITH GPUS] (TODO)
	### Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)		### Based on [https://ieeexplore.ieee.org/abstract/document/8692354 GPredicates - GPU Implementation of Robust and Adaptive Floating-Point Predicates for Computational Geometry] (TODO)
	# Decouple Contentions managers and Load Balancing from the Meshing Procedure.		# Decouple Contentions managers and Load Balancing from the Meshing Procedure (TODO)
	# Add PDR		# Add PDR (TODO)
	# Add Smoothing		# Add Smoothing (TODO)